Do not go through LLM to embed when embedding documents #1428
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
CrackerCat
pushed a commit
to CrackerCat/anything-llm
that referenced
this pull request
Jul 31, 2024
CrackerCat
pushed a commit
to CrackerCat/anything-llm
that referenced
this pull request
Aug 1, 2024
CrackerCat
pushed a commit
to CrackerCat/anything-llm
that referenced
this pull request
Aug 2, 2024
CrackerCat
pushed a commit
to CrackerCat/anything-llm
that referenced
this pull request
Aug 3, 2024
cabwds
pushed a commit
to cabwds/anything-llm
that referenced
this pull request
Jul 3, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Pull Request Type
Relevant Issues
resolves #1420
What is in this change?
From legacy code we used to go through the LLM class to reach the
embedTextInputandembedChunksfunctions. This does not make sense to go though when callingaddDocumentsin any vector db since instantiation of an LLM can have API_KEY requirements and makes no sense, since the LLM is not even called during this operation.We move now to just grabbing the embedder engine alone and do the query directly on the class instead of via a passthrough on the LLM provider. It can still be accessed through the LLM class and needs to be for prompt embedding, but this eliminate the need on uploading only to have a valid LLM key.
Additional Information
Developer Validations
yarn lintfrom the root of the repo & committed changes